karpathy-wiki-capture

REVIEW · 62
Registry indexed

Capture-authoring protocol for the main agent. Read on demand when a TRIGGER fires (per `using-karpathy-wiki/SKILL.md`). Defines how to format a capture, how to invoke `bin/wiki capture`, body-size floors, and the subagent-report workflow.

Verified installs0
Stars101
Version1.0.0
Quality67/100 · Promising
Trust62/100 · Sandbox only
Audit77/100 · Needs review

Supply asset profile

Research and knowledge work

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

Browse track

Scenario

Research agents

I need my agent to research a topic, compare sources, and produce a concise report.

Agent fit

Claude Code + CLI + Codex

Codex, Claude Code, Cursor, CLI, or custom agents.

Install

Ready

npx skills add toolboxmd/karpathy-wiki --skill karpathy-wiki-capture

Maintenance

fresh

2d since push

Risk

Needs review

Permission surface may require sandboxing

GitHub quality

101

67/100 Quality · 70/100 Trust

Coverage tags

ResearchResearch agentsautomationagent-skill

Review notes

Permission surface may require sandboxing · The skill references internal commands (bin/wiki capture, wiki ingest-now, wiki tick) without explaining their availability or fallback behavior, which could cause confusion if the environment lacks them.

Agent adoption scorecard

Trust, audit, and install readiness at a glance

These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.

Quality

Promising
67

Useful candidate, but compare it with alternatives before adopting.

Trust

Sandbox only
62

Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.

Audit

Needs review
77

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

OpenAgentSkill Trust Score v5

Human review before install

Run only in a sandbox and compare close alternatives before using it for real work.

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

101 GitHub stars

Repo activity

101 stars, 24 forks

Maintenance

2d since push

License

MIT

Install

npx skills add toolboxmd/karpathy-wiki --skill karpathy-wiki-capture

Install safety

standard package or runtime install path

Permission surface

shell or command execution, filesystem or document access

Agent outcomes

No agent outcome data yet

Docs

Strong README/SKILL.md context

Risk summary

Review before production

  • The skill references internal commands (bin/wiki capture, wiki ingest-now, wiki tick) without explaining their availability or fallback behavior, which could cause confusion if the environment lacks them.
  • Quality score needs review
  • Permission surface needs review: shell or command execution, filesystem or document access
  • Stars/forks activity: 101 stars, 24 forks; issue activity unavailable in current metadata

Install readiness

Install path available

  • Install path is available
  • Repository evidence is available
  • License is declared
  • No Agent Proven outcome evidence yet

Agent-readable metadata

Machine-readable decision data for this skill.

Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.

Open JSON

Suited tasks

  • Research agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects
  • Search sources

Suited agents

CodexClaude CodeCursorOpenAgentSkill CLICLI

Install decision

Command
npx skills add toolboxmd/karpathy-wiki --skill karpathy-wiki-capture
Policy
review
Human review
yes

Trust and risk

Trust
62/100
Audit
77/100
Risk level
Needs review

Outcome loop

Endpoint
/api/agent/outcome
Event ID
resolve
Outcomes
5

Install command

npx skills add toolboxmd/karpathy-wiki --skill karpathy-wiki-capture

Do not use when

  • teams that need a vendor-supported SLA
  • production agents without a repository review
  • The skill references internal commands (bin/wiki capture, wiki ingest-now, wiki tick) without explaining their availability or fallback behavior, which could cause confusion if the environment lacks them.
  • High-risk permission hints: Shell or command execution
  • Permission surface may require sandboxing
No close alternatives indexed yet.

Agent safety v2

45/100 · Avoid automatic install

Experimentalreview

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

Test manually in an isolated workspace and compare against safer alternatives.

Resolve via API

high

Shell or command execution

Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.

medium

Network access

Skill likely fetches remote pages, APIs, repositories, or external services.

medium

Filesystem access

Skill may read or write project files, documents, generated artifacts, or local workspace state.

medium

Database access

Skill may inspect schemas, query databases, or work with persistent stores.

  • High-risk permission hints: Shell or command execution
  • Permission surface may require sandboxing

Install targets

Install this skill in your agent workflow

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install toolboxmd-karpathy-wiki-capture

Agent resolve plan

Let an agent verify fit before installing.

The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.

Open text plan

Agent should check

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Copy prompt

Task: Use karpathy-wiki-capture in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20karpathy-wiki-capture%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/toolboxmd-karpathy-wiki-capture/install
Install command: npx skills add toolboxmd/karpathy-wiki --skill karpathy-wiki-capture
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent handoff

Give an agent the install path, not another directory page.

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

Open install API

Agent prompt

Use karpathy-wiki-capture for this task. Review https://www.openagentskill.com/api/skills/toolboxmd-karpathy-wiki-capture/install, then install with: npx skills add toolboxmd/karpathy-wiki --skill karpathy-wiki-capture

Registry metadata

Agent-readable profile for automatic skill selection.

This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.

Open manifest

Agent fit

68/100

Research agents

Platforms

Claude Code

Audit report

Needs review · 77/100

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

View audit reportView eval report

Agent decision cockpit

Fallback candidate for Research agents

Prototype with this skill first; keep a fallback candidate ready.

68
Readiness
Prototype
Stage

Role in stack

Fallback candidate

Primary fit

Research agents

Trust label

Prototype first

Install path

Command ready

Use when

  • Research agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects

Evidence

  • recent repository activity
  • install command or GitHub repo available
  • 67/100 quality profile
  • 5 OpenAgentSkill engagement events

review first

  • The skill references internal commands (bin/wiki capture, wiki ingest-now, wiki tick) without explaining their availability or fallback behavior, which could cause confusion if the environment lacks them.

Implementation path

  1. 1Install it in a sandbox agent and run one Research agents task end to end.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Trust profile

Sandbox only

Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.

62
OpenAgentSkill Trust Score

GitHub adoption

INFO

101 GitHub stars

Stars/forks activity

CHECK

101 stars, 24 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

2d since push

License clarity

PASS

MIT

Good signals

  • AI review approved
  • Install path is available
  • Repository evidence is available
  • Recently maintained repository
  • Install command has no obvious high-risk pattern
  • Outcome loop is ready but needs first real agent run

Review before install

  • The skill references internal commands (bin/wiki capture, wiki ingest-now, wiki tick) without explaining their availability or fallback behavior, which could cause confusion if the environment lacks them.
  • Quality score needs review
  • Permission surface needs review: shell or command execution, filesystem or document access
  • Stars/forks activity: 101 stars, 24 forks; issue activity unavailable in current metadata
  • Permission surface: shell or command execution, filesystem or document access
  • No real agent outcome reports yet
  • Human review required before unattended installation

Recommended action

Run only in a sandbox and compare close alternatives before using it for real work.

Quality profile

Promising candidate for agent workflows

Useful candidate, but compare it with alternatives before adopting.

67
GitHub stars
101
Freshness
2d ago
Install ready
Yes
License
MIT
Review before install: The skill references internal commands (bin/wiki capture, wiki ingest-now, wiki tick) without explaining their availability or fallback behavior, which could cause confusion if the environment lacks them.

Workflow fit

Use this skill in these scenarios

Workflow fit

Add it to a complete workflow

Overview

--- name: karpathy-wiki-capture description: | Capture-authoring protocol for the main agent. Read on demand when a TRIGGER fires (per `using-karpathy-wiki/SKILL.md`). Defines how to format a capture, how to invoke `bin/wiki capture`, body-size floors, and the subagent-report workflow. ---

# karpathy-wiki capture

You loaded this skill because a TRIGGER fired (per the loader). Your job is to write a capture file (or move a file into `inbox/` for raw-direct ingest), then return to the user's task.

## Single capture entry point

All chat-driven captures go through ONE command:

```bash echo "$BODY" | bin/wiki capture \ --title "<one-line title>" \ --kind chat-only \ --suggested-action create|update|augment ```

For chat-attached (a real file accompanies the conversation), pass the absolute path of that file via `--evidence-path`:

```bash echo "$BODY" | bin/wiki capture \ --title "<one-line title>" \ --kind chat-attached \ --suggested-action create|update|augment \ --evidence-path /absolute/path/to/source/file.ext ```

Or for long bodies:

```bash bin/wiki capture \ --title "<one-line title>" \ --kind chat-only \ --suggested-action create \ --body-file /tmp/body.md ```

`--evidence-path` is REQUIRED for `--kind chat-attached` and `--kind raw-direct`, REJECTED for `--kind chat-only`. The path lands verbatim in the capture's `evidence:` frontmatter and propagates to the manifest's `origin` field — the iron-rule contract that lets the ingester trace every wiki page back to its source.

`bin/wiki capture` handles wiki resolution (which wiki the capture goes to), prompts the user for setup if needed, writes every capture file, and asks the bounded dispatcher to drain the target queue. You do NOT write to `.wiki-pending/` directly or launch a provider yourself.

## Trigger

Triggers are listed in the loader (`using-karpathy-wiki/SKILL.md`). This skill assumes a trigger has fired and you're now writing.

## Capture file format

See `references/capture-schema.md` for the canonical frontmatter schema. Key fields you set when invoking `bin/wiki capture`:

- `--title`: one-line title (becomes filename slug + capture title). - `--kind`: `chat-only` (no file evidence) | `chat-attached` (file + conversation delta) | `raw-direct` (you do NOT write this; it's for drop-zone ingestion). - `--suggested-action`: `create` (new page) | `update` (replace existing) | `augment` (add to existing).

The body is read from stdin OR `--body-file <path>`.

## Body sufficiency

Per `references/capture-schema.md`:

| Kind | Floor | What goes in the body | |---|---|---| | `chat-only` | 1500 b | Every durable claim, exact details (URLs, version numbers, error messages), every decision-with-rationale, every gotcha, sources cited. | | `chat-attached` | 1000 b | The conversation-delta — what the conversation added that the file doesn't cover. The file is the bulk; you owe the delta in full. | | `raw-direct` | none | You don't write raw-direct bodies. The SessionStart hook or `wiki ingest-now` auto-generates them when a file appears in `inbox/`. |

A `chat-only` body must clear 1500 bytes with content, not filler. Required:

- Every durable CLAIM — fact, number, version, commit, percentage, decision. - Every CONCRETE DETAIL the ingester cannot guess — exact URLs, package names, error messages, command snippets, code examples (5-15 lines), numeric thresholds, version ranges. - Every DECISION made WITH its rationale — *"we chose X because Y failed on Z"* is a complete unit. *"we chose X"* alone is not. - Every CONTRADICTION, GOTCHA, OR CAVEAT observed. - SOURCES — doc URLs, arxiv IDs, GitHub repos with star counts as-of the session.

NOT in the body:

- Pleasantries, meta-commentary, "let me check", "good question". - Process over output: wrong turns, reasoning trail, "I thought X but then Y". Keep the resolution; drop the detour. - The user's questions verbatim — they're context, not content. Capture the ANSWER, not the question.

If the ingester rejects your capture (`needs_more_detail: true`), expand the re-queued body in place, remove both `needs_more_detail` and `needs_more_detail_reason` from frontmatter, and run `wiki tick <wiki> --source manual`. Marked captures remain durable but are not automatically retried. Do NOT ignore the rejection.

## Subagent reports — DO NOT write a capture body

When a research subagent returns a file with durable findings, the report IS the capture. Move the file to `<wiki>/inbox/`:

```bash mv <subagent-report-path> <wiki>/inbox/<basename> wiki ingest-now <wiki> # or wait for next SessionStart ```

`wiki ingest-now` triggers the same drift-scan + drain that SessionStart runs, but on demand. Use this when the user is still in the active session and wants the report ingested before they close the terminal.

Subagent-report bodies frequently exceed several KB; rewriting them as a `chat-only` capture body wastes tokens AND produces an inferior wiki page (the body summarizes what the file already says).

## Mode change

If the user asks to change the wiki mode for this directory:

```bash wiki use project # captures go to ./wiki/ only wiki use main # captures go to ~/wiki/ only wiki use both # capture locally; selectively promote reusable knowledge ```

Confirm in one line. The mode is persisted in `<cwd>/.wiki-config` (project or both) or `<cwd>/.wiki-mode` (main-only). See `references/capture-schema.md` and the v2.4 spec for details.

`both` is project-first. The original capture is written only to `./wiki/`. During ingest, the project ingester keeps project-specific knowledge local and uses the deterministic promotion helper only for reusable cross-project knowledge. The original capture is never copied verbatim to both queues.

## Cwd unconfigured (0.2.9)

If `bin/wiki capture` aborts with stderr containing `cwd unconfigured` + a `wiki use project|main|both` nudge, the cwd has no `.wiki-config` or `.wiki-mode`. The body is preserved at the orphan path printed in the same stderr. Do NOT silently re-route or auto-pick — surface the choice to the user verbatim:

> "This directory isn't configured for the wiki yet. Should this > capture go to: (a) a project wiki at `./wiki/` (scoped to this > repo), (b) the main wiki at `~/wiki/` (cross-project), or (c) both?"

After the user picks, run `wiki use project|main|both` and re-capture either by re-piping the body or by passing the orphan path:

```bash bin/wiki capture --title "..." --kind chat-only \ --suggested-action create --body-file <orphan-path> ```

Pre-0.2.9 the CLI silently auto-selected `main-only` and wrote `<cwd>/.wiki-mode`, stealing the choice from the user. The new abort makes the choice explicit.

## Order matters: reply first, then capture

Reply to the user FIRST. The user is waiting; capture mechanics are not. After your reply emits, write any captures whose triggers fired (via `bin/wiki capture`), then run a turn-closure check.

## Turn closure — before you stop

Before emitting your final assistant message, check:

```bash ls "<wiki_root>/.wiki-pending/" 2>/dev/null | grep -v '^archive$\|^schema-proposals$' | head -20 ```

If the output lists any `.md` file OR any `.md.processing` file older than 10 minutes, the turn is NOT done. Handle the pending captures first (rejection-handling, stalled-recovery, missed-capture from earlier turns), then re-check, then close the turn.

This is a self-discipline rule until a Stop-hook gate is wired.

## What's NOT in this skill

- The ingester's behavior (orientation, page format, manifest protocol). That lives in `karpathy-wiki-ingest/SKILL.md` and is loaded by the detached runtime ingester only. The main agent never reads it. - Iron laws and announce-line contract. Those live in the loader (`using-karpathy-wiki/SKILL.md`) — single source of truth.

Technical details

Version
1.0.0
License
MIT
Last updated
Aug 20, 2026
Published
Aug 20, 2026

Decision snapshot

Fallback candidate

68
Ready
Prototype
Stage

recent repository activity

Audit

Install review

Install and adoption review

77
Needs review
Security
76/100
Maintenance
100/100
Install
92/100
Open full auditView eval report

Agent-proven evidence

Agent-proven evidence

Outcome reports after resolve, review, install, and one narrow run.

0
Proven
Needs first agent runAuto-install: review firstLast: Unknown
Success rate
Recent failure
Outcomes
0
Output quality
Failed
0
Not relevant
0
Installs
0
Risk blocked
0
Setup needed
0
Production
0

No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.

Install

Add to agent workflow

Free and open source. Review the report before installing into production agents.

Growth loop

Share kit

X

Scenario-led draft for karpathy-wiki-capture, ready for a manual X post.

Curator note
karpathy-wiki-capture: Capture-authoring protocol for the main agent. Read on demand when a TRIGGER fires (per `usin...

101 stars

https://www.openagentskill.com/skills/toolboxmd-karpathy-wiki-capture?ref=x
Open X draft
Optional reply with install command
Listing + install path for karpathy-wiki-capture:
https://www.openagentskill.com/skills/toolboxmd-karpathy-wiki-capture?ref=x

Install: npx skills add toolboxmd/karpathy-wiki --skill karpathy-wiki-capture

Listing source

Registry indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

Creator
toolboxmd
Indexed by
OpenAgentSkill community index

Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.

Claim this skill

Owner claim

Claim this skill listing

This Registry indexed listing is attributed to toolboxmd but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.

Creator backlink kit

Add the evidence badges to your README

Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/toolboxmd-karpathy-wiki-capture?metric=listed&label=Listed)](https://www.openagentskill.com/skills/toolboxmd-karpathy-wiki-capture)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/toolboxmd-karpathy-wiki-capture?metric=trust&label=Trust)](https://www.openagentskill.com/skills/toolboxmd-karpathy-wiki-capture)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/toolboxmd-karpathy-wiki-capture?metric=audit&label=Audit)](https://www.openagentskill.com/skills/toolboxmd-karpathy-wiki-capture/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/toolboxmd-karpathy-wiki-capture?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/toolboxmd-karpathy-wiki-capture)

Author

T

toolboxmd

@toolboxmd

Platform fit

Health signals

GitHub stars
101
Quality score
37/100
Last GitHub push
Aug 20, 2026
Framework hints
Unknown
OpenAgentSkill views
5
Install copies
0
Outbound clicks
0

Community signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.

Trust & safety

Sandbox only

62
  • GitHub adoption101 GitHub starsINFO
  • Stars/forks activity101 stars, 24 forks; issue activity unavailable in current metadataCHECK
  • Recent maintenance2d since pushPASS
  • License clarityMITPASS
  • README/SKILL.md completenessMetadata includes enough usage and workflow contextPASS
  • Dependency/runtime riskcommand execution surfaceINFO